© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22122
    Prev
    Next
    INDEX
    Explanations

    origins and beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of origins, specifically spotting the word “beginning” or “beginnings.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    栳
    -2.91
    鬭
    -2.67
     iſt
    -2.41
    塒
    -2.36
     Kopi
    -2.36
     VIET
    -2.31
     BIBLIO
    -2.22
     lage
    -2.22
     Lagi
    -2.20
     successivamente
    -2.19
    POSITIVE LOGITS
     Some
    2.31
     Importantly
    2.31
     Now
    2.20
     Perhaps
    2.11
     Possibly
    2.11
    ſelves
    2.08
     Sometimes
    2.06
     Notably
    2.05
     Much
    1.98
     Mostly
    1.97
    Activations Density 0.011%

    No Known Activations